© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 108460
    Prev
    Next
    INDEX
    Explanations

    CSS style properties related to layout and positioning

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ignum
    -0.07
    udas
    -0.07
    请
    -0.07
    ambre
    -0.07
    yn
    -0.06
    ãĥ¬ãĥ³
    -0.06
    898
    -0.06
     ãģ¨
    -0.06
     sitting
    -0.06
    íıIJ
    -0.06
    POSITIVE LOGITS
    isse
    0.08
     Sche
    0.06
    usz
    0.06
    oyo
    0.06
    ernet
    0.06
    attach
    0.06
    913
    0.06
    æĸ¹
    0.06
    eree
    0.06
    usted
    0.06
    Activations Density 0.005%

    No Known Activations